### Check for existing issues

- [x] I have searched the existing issues and checked that my issue is not a duplicate.

### What happened?

I've setup LiteLLM on kubernetes with the following configuration

``` image: repository: ghcr.io/berriai/litellm-database tag: "v1.85.0-rc.1"

[...]

proxy_config: model_list: - model_name: chatgpt/gpt-5.5 model_info: mode: responses litellm_params: model: chatgpt/gpt-5.5 general_settings: ```

I checked the logs of LiteLLM and followed the auth process which worked fine, I now have the model in the litellm UI

<img width="2152" height="294" alt="Image" src="https://github.com/user-attachments/assets/9e0c89c3-c415-42fc-81a0-c2c49debd1a1" />

However, if I go in the model and I click on "Test Connection" I get the following error

<img width="954" height="410" alt="Image" src="https://github.com/user-attachments/assets/b1e53977-1c6b-4db0-816f-ada914228411" />

If I check the network tab to see the error I get

```json { "status": "error", "result": { "use_in_pass_through": false, "use_litellm_proxy": false, "merge_reasoning_conten…